End of training
Browse files
README.md
CHANGED
@@ -3,9 +3,15 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
5 |
tags:
|
|
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: zephyr-7b-align-scan-0.0-0.3-linear-3
|
11 |
results: []
|
@@ -16,17 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# zephyr-7b-align-scan-0.0-0.3-linear-3
|
18 |
|
19 |
-
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Rewards/chosen: -3.
|
23 |
-
- Rewards/rejected: -
|
24 |
- Rewards/accuracies: 0.3413
|
25 |
-
- Rewards/margins: 1.
|
26 |
-
- Logps/rejected: -
|
27 |
-
- Logps/chosen: -
|
28 |
-
- Logits/rejected: -2.
|
29 |
-
- Logits/chosen: -2.
|
30 |
|
31 |
## Model description
|
32 |
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: alignment-handbook/zephyr-7b-sft-full
|
5 |
tags:
|
6 |
+
- alignment-handbook
|
7 |
- trl
|
8 |
- dpo
|
9 |
- generated_from_trainer
|
10 |
+
- trl
|
11 |
+
- dpo
|
12 |
+
- generated_from_trainer
|
13 |
+
datasets:
|
14 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
15 |
model-index:
|
16 |
- name: zephyr-7b-align-scan-0.0-0.3-linear-3
|
17 |
results: []
|
|
|
22 |
|
23 |
# zephyr-7b-align-scan-0.0-0.3-linear-3
|
24 |
|
25 |
+
This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the HuggingFaceH4/ultrafeedback_binarized dataset.
|
26 |
It achieves the following results on the evaluation set:
|
27 |
+
- Loss: 0.8855
|
28 |
+
- Rewards/chosen: -3.8900
|
29 |
+
- Rewards/rejected: -5.1926
|
30 |
- Rewards/accuracies: 0.3413
|
31 |
+
- Rewards/margins: 1.3027
|
32 |
+
- Logps/rejected: -97.0942
|
33 |
+
- Logps/chosen: -86.4517
|
34 |
+
- Logits/rejected: -2.4499
|
35 |
+
- Logits/chosen: -2.4705
|
36 |
|
37 |
## Model description
|
38 |
|
all_results.json
CHANGED
@@ -1,5 +1,18 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.4743386713994874,
|
5 |
"train_runtime": 3246.9146,
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -2.470487117767334,
|
4 |
+
"eval_logits/rejected": -2.4498531818389893,
|
5 |
+
"eval_logps/chosen": -86.45170593261719,
|
6 |
+
"eval_logps/rejected": -97.09423065185547,
|
7 |
+
"eval_loss": 0.8855458498001099,
|
8 |
+
"eval_rewards/accuracies": 0.341269850730896,
|
9 |
+
"eval_rewards/chosen": -3.889953851699829,
|
10 |
+
"eval_rewards/margins": 1.3026951551437378,
|
11 |
+
"eval_rewards/rejected": -5.1926493644714355,
|
12 |
+
"eval_runtime": 137.5858,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 14.536,
|
15 |
+
"eval_steps_per_second": 0.458,
|
16 |
"total_flos": 0.0,
|
17 |
"train_loss": 0.4743386713994874,
|
18 |
"train_runtime": 3246.9146,
|
config.json
CHANGED
@@ -22,6 +22,6 @@
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.2",
|
25 |
-
"use_cache":
|
26 |
"vocab_size": 32000
|
27 |
}
|
|
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.2",
|
25 |
+
"use_cache": true,
|
26 |
"vocab_size": 32000
|
27 |
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -2.470487117767334,
|
4 |
+
"eval_logits/rejected": -2.4498531818389893,
|
5 |
+
"eval_logps/chosen": -86.45170593261719,
|
6 |
+
"eval_logps/rejected": -97.09423065185547,
|
7 |
+
"eval_loss": 0.8855458498001099,
|
8 |
+
"eval_rewards/accuracies": 0.341269850730896,
|
9 |
+
"eval_rewards/chosen": -3.889953851699829,
|
10 |
+
"eval_rewards/margins": 1.3026951551437378,
|
11 |
+
"eval_rewards/rejected": -5.1926493644714355,
|
12 |
+
"eval_runtime": 137.5858,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 14.536,
|
15 |
+
"eval_steps_per_second": 0.458
|
16 |
+
}
|
runs/Sep24_11-44-10_qa-a100-004.crc.nd.edu/events.out.tfevents.1727196315.qa-a100-004.crc.nd.edu.1827364.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb77121778605f7f36ecd67a343717f32f11c513e49ee245c130c9f742808c7a
|
3 |
+
size 828
|